Mathematical Optimization Modeling on IndustryOR
89.9AccuracyTriVAL
Evaluation results
| Method | Links | ||
|---|---|---|---|
| TriVALModel=DeepSeek-V3.2, Method category=Prompt-based2026.05 | 89.9 | 88.8 | |
| TriVALModel=GPT-5.1, Method category=Prompt-based2026.05 | 86.9 | 86.9 | |
| OR-LLM-AgentModel=GPT-5.1, Method category=Prompt-based2026.05 | 78.8 | 81.8 | |
| OR-LLM-AgentModel=DeepSeek-V3.2, Method category=Prompt-based2026.05 | 77.8 | 76.8 | |
| OptiTreeModel=GPT-5.1, Method category=Prompt-based2026.05 | 75.8 | 74.1 | |
| OptiTreeModel=DeepSeek-V3.2, Method category=Prompt-based2026.05 | 67.7 | 71.2 | |
| AutoFormulationModel=DeepSeek-V3.2, Method category=Prompt-based2026.05 | 63.6 | 50.1 | |
| SIRLMethod category=Learning-based2026.05 | 52.5 | 54.9 | |
| AutoFormulationModel=GPT-5.1, Method category=Prompt-based2026.05 | 52.5 | 52.1 | |
| LLMOPTMethod category=Learning-based2026.05 | 38.4 | 31.9 | |
| ORLMMethod category=Learning-based2026.05 | 34.3 | 29.1 |